© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11694
    Prev
    Next
    INDEX
    Explanations

    phrases related to focus and relaxation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of effort and perseverance in difficult situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itol
    -0.70
    天
    -0.66
    Ö¼
    -0.65
    itor
    -0.62
    USD
    -0.61
     blight
    -0.60
    ura
    -0.60
    stros
    -0.60
     Pigs
    -0.60
    FER
    -0.60
    POSITIVE LOGITS
     lest
    0.96
     maneu
    0.72
     mindful
    0.69
    rouse
    0.67
     directions
    0.67
     responsiveness
    0.67
     diligent
    0.66
     relaxation
    0.64
     meditation
    0.64
     manoeuv
    0.63
    Activations Density 0.810%

    No Known Activations